© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13614
    Prev
    Next
    INDEX
    Explanations

    mentions of Pakistani politicians, political parties, and constituencies in Pakistan

    oai_token-act-pair · gemini-2.0-flash

    Proper nouns and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     writeTo
    -0.44
    {{
    -0.44
     bay
    -0.43
    abelle
    -0.41
    ctin
    -0.40
     animate
    -0.40
     Tän
    -0.39
     Sitten
    -0.39
    onComplete
    -0.39
    ни
    -0.39
    POSITIVE LOGITS
    reportWebVitals
    0.81
     NSCoder
    0.73
    UseVisualStyle
    0.73
    enfone
    0.71
    RectangleBorder
    0.71
     HasFactory
    0.69
    Statistiche
    0.68
     '{@
    0.67
    SourceChecksum
    0.66
    libft
    0.66
    Activations Density 2.415%

    No Known Activations